2024
NIPS
NeurIPS 2024
Equivariant Neural Diffusion for Molecule Generation
Abstract
We introduce Equivariant Neural Diffusion (END), a novel diffusion model for molecule generation in 3D that is equivariant to Euclidean transformations. Compared to current state-of-the-art equivariant diffusion models, the key innovation in END lies in its learnable forward process for enhanced generative modelling. Rather than pre-specified, the forward process is parameterized through a time- and data-dependent transformation that is equivariant to rigid transformations. Through a series of experiments on standard molecule generation benchmarks, we demonstrate the competitive performance of END compared to several strong baselines for both unconditional and conditional generation.
🧭
Keyword Pioneer
— equivariant diffusion
🐝
Cross-Pollinator
— Artificial Intelligence, Computer Vision, Data Science & Analytics, Deep Learning, Healthcare & Medicine, Interdisciplinary, Knowledge & Reasoning, Machine Learning, Mathematics & Optimization, Natural Language Processing, Reinforcement Learning, Robotics, Speech & Audio
🌉
Interdisciplinary Bridge
— Deep Learning and Interdisciplinary and Machine Learning
Authors
Topics
Deep Learning > Architectures > Graph Neural Networks
Deep Learning > Models > Diffusion Models
Interdisciplinary > Science > Quantum Computing
Machine Learning > Learning Types > Deep Learning
Machine Learning > Learning Types > Generative Models
Machine Learning > Learning Types > Generative Model
Deep Learning > Learning Types > Generative Models